Content-based image retrieval

About: Content-based image retrieval is a research topic. Over the lifetime, 6916 publications have been published within this topic receiving 150696 citations. The topic is also known as: CBIR.

Content-based image retrieval using joint correlograms

Abstract: The comparison of digital images to determine their degree of similarity is one of the fundamental problems of computer vision. Many techniques exist which accomplish this with a certain level of success, most of which involve either the analysis of pixel-level features or the segmentation of images into sub-objects that can be geometrically compared. In this paper we develop and evaluate a new variation of the pixel feature and analysis technique known as the color correlogram in the context of a content-based image retrieval system. Our approach is to extend the autocorrelogram by adding multiple image features in addition to color. We compare the performance of each index scheme with our method for image retrieval on a large database of images. The experiment shows that our proposed method gives a significant improvement over histogram or color correlogram indexing, and it is also memory-efficient.

Content Based Image Retrieval using Advanced Color and Texture Features

Abstract: The paper presents an efficient Content Based Image Retrieval (CBIR) system using color and texture. In proposed system, two different feature extraction techniques are employed. A universal content based image retrieval system uses color, texture and shape based feature extraction techniques for better matched images from the database. In proposed CBIR system, color and texture features are used. The texture features were extracted from the query image by applying block wise Discrete Cosine Transforms (DCT) on the entire image and from the retrieved images the color features were extracted by using moments of colors (Mean, Deviation and Skewness) theory. The proposed system has used Corel database of 1000 images. The feature vectors of the query image will then be compared with feature vectors of the database to obtain similar images. Individual and combined vectors using color and texture features were computed and the combined feature vector results were comparatively better. The proposed system provides an efficiency of 60%.

Content-based Image Retrieval by Ontology-based Object Recognition

Abstract: The main disadvantage of image retrieval systems is their lack of domain knowledge. Therefore a retrieval system has to focus on primitive features, as Eakins and Graham name them [3]. Due to the lack of background knowledge of the domain, the retrieval error rate is usually dissatisfying or the search options are limited to syntactic queries. Knowledgebased techniques allow for semantical searches filling the “semantical gap” [4]. In this paper we present a supervised learning system OntoPic, which is based on the well-known ontologies coded in DAML+OIL, for providing the domain knowledge. Combined with a DL reasoner for ontologies, the main target is to achieve a new level of result quality while allowing semantical searches. The main advantage of this approach is the usage of the reasoner as a classifier, enabling a dual use of the ontology. The same domain knowledge can be used for better object recognition, the basis for satisfying results, and a semantical search. Our work is applied to the domain of landscape images.

Analyzing Low-Level Visual Features Using Content-Based Image Retrieval

Abstract: This paper describes how low-level statistical visual features can be analyzed in our content-based image retrieval system named PicSOM. The lowlevel visual features used in the system are all statistical by nature. They include average color, color moments, contrast-type textural feature, and edge histogram and Fourier transform based shape features. Other features can be added easily. A genuine characteristic of the PicSOM system is to use relevance feedback from the human user’s actions to direct the system in scoring the relevance of particular features in the present query. While the link from features to semantic concepts remains an open problem, it is possible to relate low-level features to subjective image similarity, as perceived instantaneously by human users. The efficient implementation of PicSOM allows tests using statistically sufficiently large and representative databases of natural images.

Mean version space: a new active learning method for content-based image retrieval

Abstract: In content-based image retrieval, relevance feedback has been introduced to narrow the gap between low-level image feature and high-level semantic concept. Furthermore, to speed up the convergence to the query concept, several active learning methods have been proposed instead of random sampling to select images for labeling by the user. In this paper, we propose a novel active learning method named mean version space, aiming to select the optimal image in each round of relevance feedback. Firstly, by diving into the lemma that motivates support vector machine active learning method (SVMactive), we come up with a new criterion which is tailored for each specific learning task and will lead to the fastest shrinkage of the version space in all cases. The criterion takes both the size of the version space and the posterior probabilities into consideration, while existing methods are only based on one of them. Moreover, although our criterion is designed for SVM, it can be justified in a general framework. Secondly, to reduce processing time, we design two schemes to construct a small candidate set and evaluate the criterion for images in the set instead of all the unlabeled images. Systematic experimental results demonstrate the superiority of our method over existing active learning methods